高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于M值概率分布的网络视频流分类

杨凌云 董育宁 王再见 汤萍萍

杨凌云, 董育宁, 王再见, 汤萍萍. 基于M值概率分布的网络视频流分类[J]. 电子与信息学报, 2018, 40(5): 1094-1100. doi: 10.11999/JEIT170617
引用本文: 杨凌云, 董育宁, 王再见, 汤萍萍. 基于M值概率分布的网络视频流分类[J]. 电子与信息学报, 2018, 40(5): 1094-1100. doi: 10.11999/JEIT170617
YANG Lingyun, DONG Yuning, WANG Zaijian, TANG Pingping. Network Video Traffic Classification Based on Probability Distribution of M Value[J]. Journal of Electronics and Information Technology, 2018, 40(5): 1094-1100. doi: 10.11999/JEIT170617
Citation: YANG Lingyun, DONG Yuning, WANG Zaijian, TANG Pingping. Network Video Traffic Classification Based on Probability Distribution of M Value[J]. Journal of Electronics and Information Technology, 2018, 40(5): 1094-1100. doi: 10.11999/JEIT170617

基于M值概率分布的网络视频流分类

doi: 10.11999/JEIT170617
基金项目: 

国家自然科学基金(61271233, 61401004, 61601005),华为HIRP创新项目,安徽师范大学博士科研启动金项目(2016XJJ129)

Network Video Traffic Classification Based on Probability Distribution of M Value

Funds: 

The National Natural Science Foundation of China (61271233, 61401004, 61601005), The HIRP Program of Huawei Technology Co. Ltd, The Ph.D Programs Foundation of Anhui Normal University (2016XJJ129)

  • 摘要: 为了改善网络视频流的细粒度分类效果,该文分析视频流传输过程中的特征变化与流分类之间的关系。根据不同类型的视频流具有不同的下行传输速率变化模式,提出一种新的基于下行速率传输的视频流分类特征--M值概率分布,并使用支持向量机(SVM)实现网络视频流的分类。实验结果表明,M值概率分布相比较于已有的常见流特征,可以更好地实现6种典型的网络视频流分类。
  • [1] KESAVARAJ G and SUKUMARAN S. A study on classification techniques in data mining[C]. Proceedings of the 4th International Conference on Computing, Communications and Networking Technologies, Tiruchengode, India, 2014: 1-7. doi: 10.1109/ICCCNT.2013. 6726842.
    [2] ANDERSSON R. Classification of video traffic: An evaluation of video traffic classification using random forests and gradient boosted trees[D]. [Master dissertation], Karlstad University, 2017.
    [3] GHOFRANI F, JAMSHIDI A, and KESHAVARZ- HADDAD A. Internet traffic classification using Hidden Naive Bayes model[C]. Proceedings of the 23rd Iranian Conference on Electrical Engineering, Tehran, Iran, 2015: 235-240. doi:  10.1109/IranianCEE.2015.7146216.
    [4] MUNTHER A, ALALOUSI A, NIZAM S, et al. Network traffic classificationA comparative study of two common decision tree methods: C4.5 and Random forest[C]. Proceedings of the 2nd International Conference on Electronic Design, Penang, Malaysia, 2014: 210-214. doi:  10.1109/ICED.2014.7015800.
    [5] HAO Shengnan, HU Jing, LIU Songyin, et al. Improved SVM method for internet traffic classification based on feature weight learning[C]. Proceedings of the Fourth International Conference on Control, Automation and Information Sciences (ICCAIS) Changshu, China, 2015: 102-106. doi:  10.1109/ICCAIS.2015.7338641.
    [6] VINUSHREE N, HEMALATHA B, and KALIAPPAN V K. Efficient kernel-based fuzzy C-means clustering for pest detection and classification[C]. Proceedings of the 2014 Computing and Communication Technologies (WCCCT), Tamilnadu, India, 2014: 179-181. doi: 10.1109/WCCCT. 2014.61.
    [7] ZHANG Shichao, LI Xuelong, ZONG Ming, et al. Efficient kNN classification with different numbers of nearest neighbors[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017: 1-12. doi: 10.1109/TNNLS.2017. 2673241.
    [8] WANG Pu, LIN Shihchun, and LUO Min. A framework for QoS-aware traffic classification using semi-supervised machine learning in SDNs[C]. Proceedings of the 13th IEEE International Conference on Services Computing, San Francisco, USA, 2016: 760-765. doi:  10.1109/SCC.2016.133.
    [9] GLENNAN T, LECKIE C, and ERFANI S M. Improved classification of known and unknown network traffic flows using semi-supervised machine learning[C]. Proceedings of the Australasian Conference on Information Security and Privacy, QLD, Australia, 2016: 493-501. doi: 10.1007/978- 3-319-40367-0-33.
    [10] BAGHERZADEH-KHIAVANI F, RAMEZANKHANI A, AZIZI F, et al. A tutorial on variable selection for clinical prediction models: Feature selection methods in data mining could improve the results[J]. Journal of Clinical Epidemiology, 2016(71): 76-85. doi: 10.1016/j.jclinepi.2015. 10.002.
    [11] MOORE A, ZUEV D, and CROGAN M. Discriminators for use in flow-based classification[R]. Queen Mary University of London, 2013: 1-14.
    [12] ZhANG JUN, YANG XIANG, WANG YU, et al. Network traffic classification using correlation information[J]. IEEE Transactions on Parallel and Distributed Systems, 2013, 24(1): 104-117. doi:  10.1109/TPDS.2012.98.
    [13] RAVEENDRAN R and MENON R R. A novel aggregated statistical feature based accurate classification for internet traffic[C]. Proceedings of the 16 International Conference on Data Mining and Advanced Computing (SAPIENCE), Ernakulam, India, 2016: 225-232. doi: 10.1109/SAPIENCE. 2016.7684123.
    [14] MIAO Yuantian, RUAN Zichan, PAN Lei, et al. Comprehensive analysis of network traffic data[C]. 16th IEEE International Conference on Computer and Information Technology, Nadi, FIji, 2017: 423-430. doi:  10.1109/TPDS.2012.98.
    [15] THAY C, VISOOTTIVISETH V, and MONGKOLLUKSAMEE S. P2P traffic classification for residential network[C]. Proceedings of the 2015 Computer Science and Engineering Conference (ICSEC), Chiang Mai, Thailand, 2015: 1-6. doi:  10.1109/ICSEC.2015.7401433.
    [16] HUANG Yinxiang, LI Yun, and QIANG Baohua. Internet traffic classification based on min-max ensemble feature selection[C]. 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, Canada, 2016: 3485-3492. doi:  10.1109/IJCNN.2016.7727646.
    [17] AUGUSTIN B and MELLOUK A. On traffic patterns of http applications[C]. Proceedings of the Global Telecommunications Conference (GLOBECOM 2011), Texas, USA, 2011: 1-6. doi:  10.1109/GLOCOM.2011.6134438.
    [18] WANG Zaijian, DONG Yuning, et al. Internet video traffic classification using QoS features[C]. Proceedings of the 2016 International Conference on Computing, Networking and Communications (ICNC), Hawaii, USA, 2016: 1-5. doi:  10.1109/ICCNC.2016.7440599.
    [19] SHAFIG M, YU X, and LAGHARI A A. WeChat text messages service flow traffic classification using machine learning technique[C]. Proceedings of the 6th International Conference on IT Convergence and Security (ICITCS), Prague, Czech, 2016: 1-5. doi:  10.1109/ICITCS.2016.7740379.
    [20] DUBIN R, HADAR O, RICHMAN I, et al. Video quality representation classification of Safari encrypted DASH streams[C]. Proceedings of the 1st Digital Media Industry Academic Forum (DMIAF). Santorini, Greece, 2016: 213-216. doi:  10.1109/DMIAF.2016.7574935.
    [21] NOVAKOVIC J. Toward optimal feature selection using ranking methods and classification algorithms[J]. Yugoslav Journal of Operations Research, 2011, 21(1): 119-135. doi:  10.2298/YJOR1101119N.
    [22] HALL M A. Correlation-based feature selection for machine learning[D]. [Ph.D. dissertation], The University of Waikato, 1999.
    [23] KONONENKO I,IMEC E, and ROBINK-IKONJA M. Overcoming the myopia of inductive learning algorithms with RELIEFF[J]. Applied Intelligence, 1997, 7(1): 39-55. doi:  10.1023/A:1008280620621.
    [24] Telecommunication Standardization Sector of ITU-2013, Parametric non-intrusive assessment of audiovisual media streaming quality[S]. 2013.
  • [1] 伊鹏, 刘洪, 胡宇翔.  一种可扩展的软件定义数据中心网络流调度策略, 电子与信息学报. doi: 10.11999/JEIT160623
    [2] 汤萍萍, 董育宁.  小波域基于分段Hurst指数的视频流分类, 电子与信息学报. doi: 10.11999/JEIT160745
    [3] 周烨, 杨旭, 李勇, 苏厉, 金德鹏, 曾烈光.  基于分类的软件定义网络流表更新一致性方案, 电子与信息学报. doi: 10.3724/SP.J.1146.2012.01431
    [4] 胡超, 陈鸣, 许博, 李兵.  实时识别P2P-TV视频流的方法研究, 电子与信息学报. doi: 10.3724/SP.J.1146.2010.00975
    [5] 卢冀, 肖嵩, 吴成柯.  一种面向视频传输的SVC码流排序方法, 电子与信息学报. doi: 10.3724/SP.J.1146.2010.00670
    [6] 刘聪, 廖建新, 王纯, 王敬宇, 张婧.  广播网络中基于补丁流的丢包恢复机制研究, 电子与信息学报. doi: 10.3724/SP.J.1146.2008.00554
    [7] 吕国云, 蒋冬梅, 樊养余, 赵荣椿, H.Sahli, W.Verhelst.  基于多流三音素DBN模型的音视频语音识别和音素切分, 电子与信息学报. doi: 10.3724/SP.J.1146.2007.01216
    [8] 孙钦东, 郭晓军, 黄新波.  基于多模式匹配的网络视频流识别与分类算法, 电子与信息学报. doi: 10.3724/SP.J.1146.2008.00301
    [9] 吕国云, 蒋冬梅, 张艳宁, 赵荣椿, HSahli, IlseRavyse .  基于多流多状态动态贝叶斯网络的音视频连续语音识别, 电子与信息学报. doi: 10.3724/SP.J.1146.2007.00915
    [10] 尤隽永, 刘贵忠, 李宏亮.  一种快速、鲁棒的压缩视频光流场估计算法, 电子与信息学报. doi: 10.3724/SP.J.1146.2006.00175
    [11] 张建龙, 吴成柯, 肖嵩, 杜建超.  一种空域可分级的自适应视频码流控制方法, 电子与信息学报.
    [12] 刘志高, 张福泰, 徐倩.  基于字的流密码的分布式解密, 电子与信息学报.
    [13] 王升辉, 裘正定.  VBR视频流多重分形建模, 电子与信息学报.
    [14] 邹仕洪, 林华生, 程时端.  DCF传输MPEG-4视频流的研究, 电子与信息学报.
    [15] 王占辉, 刘贵忠, 刘龙, 刘洁瑜.  一种从视频压缩码流中精确提取运动对象的快速算法, 电子与信息学报.
    [16] 姚兴苗, 胡光岷, 李乐民.  一种采用按值分支树的多维流分类算法, 电子与信息学报.
    [17] 黄伟红, 张福炎.  一个基于速率控制的Internet视频流服务方案, 电子与信息学报.
    [18] 奚亮, 金惠文.  自相似VBR视频源业务流的建模和仿真, 电子与信息学报.
    [19] 杨嘉湜, 吴杰, 李学田, 宋明, 童调生.  开关电流网络的信号流图分析法, 电子与信息学报.
    [20] 虞希清, 陆生勋.  产生全符号网络函数的Coates流图法, 电子与信息学报.
  • 加载中
  • 计量
    • 文章访问数:  470
    • HTML全文浏览量:  35
    • PDF下载量:  80
    • 被引次数: 0
    出版历程
    • 收稿日期:  2017-06-28
    • 修回日期:  2018-02-23
    • 刊出日期:  2018-05-19

    目录

      /

      返回文章
      返回

      官方微信,欢迎关注